© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 1826
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "new to" or similar phrases indicating newcomers or fresh experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ências
    -0.07
    namen
    -0.06
    yonel
    -0.06
    xit
    -0.06
    èħ¹
    -0.06
     tvar
    -0.06
    кап
    -0.06
    pec
    -0.06
     stron
    -0.06
    arith
    -0.06
    POSITIVE LOGITS
    asser
    0.08
    ÑĢаÑħов
    0.07
    hani
    0.07
     fold
    0.07
    ipay
    0.07
    æĬĺ
    0.07
    avez
    0.06
    orex
    0.06
    plet
    0.06
    HEEL
    0.06
    Activations Density 0.004%

    No Known Activations